最近在看 Mask R-CNN, 这个分割算法是基于 Faster R-CNN 的,决定看一下这个 R-CNN 系列论文,好好理一下
R-CNN 2014
1. 论文 Rich feature hierarchies for accurate object detection and semantic segmentation Tech report (v5)
Author: Ross Girshick Jeff Donahue Trevor Darrell Jitendra Malik, UC Berkeley
link: https://arxiv.org/pdf/1311.2524.pdf (2014)
2. 【目标检测】R-CNN论文详解(Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation)https://www.jianshu.com/p/c1696c27abf8
Ref:
- R-CNN学习总结 https://zhuanlan.zhihu.com/p/30316608
- R-CNN论文详解 https://blog.csdn.net/WoPawn/article/details/52133338 (讲懂了 bounding box 回归)
- R-CNN 论文 http://citeseerx.ist.psu.edu/viewdoc/download;jsessionid=AF8817DD0F70B32AA08B2ECBBA8099FA?doi=10.1.1.715.2453&rep=rep1&type=pdf
- Review: R-CNN (Object Detection) https://medium.com/coinmonks/review-r-cnn-object-detection-b476aba290d1
Fast R-CNN 2015
R-CNN 有两个问题:1. Selective Search 发现的~2k个region proposal 都要被送到CNN feature extractor里,实际上这2k个region 有大量重复的部分,所以造成很多重复计算. 2. 有3个model 独立训练(feature extractor, SVM classifier, bbox refine),占用大量时间
Solution: 1. 一次CNN计算完成以前 2k 次计算,, 然后用ROI Pooling把region proposal 缩放到固定大小 . 2. 合并以前的3个网络成一个整体. 用softmax代替了svm 分类器.
NOTE: 还是用到了 Select Search.
Ref:
- 【目标检测】Fast RCNN算法详解 https://blog.csdn.net/forever__1234/article/details/79919994
- https://www.mihaileric.com/posts/fast-object-detection-with-fast-rcnn/
- https://jhui.github.io/2017/03/15/Fast-R-CNN-and-Faster-R-CNN/
- http://www.robots.ox.ac.uk/~tvg/publications/talks/fast-rcnn-slides.pdf
Faster R-CNN 2016
Fast R-CNN 还是使用 Selective Search 先选取 region proposal, Faster R-CNN 使用叫RPN 的CNN网络选 region proposal
我对整个过程的理解:不用理解了,直接参考【5】就对了
Ref:
- https://www.jianshu.com/p/ab1ebddf5
- 目标检测网络之Faster-rcnn解读(二)
- https://blog.csdn.net/hejin_some/article/details/88735023
- https://zhuanlan.zhihu.com/p/66228313
- 【程序喵笔记】目标识别1.0: Faster RCNN (这个写的很清楚,总算看懂了,也讲清楚了两次 NMS)
Mask R-CNN 2017
Mask R-CNN 提供两种backbone, with ResNet 和 with FPN, 对应的的两种Head如下
图像分割算法
Ref
- https://engineering.matterport.com/splash-of-color-instance-segmentation-with-mask-r-cnn-and-tensorflow-7c761e238b46
- https://blog.csdn.net/hejin_some/article/details/88735023
Overall:
Ref
- Object Detection for Dummies Part 3: R-CNN Family
- https://www.itdaan.com/blog/2017/12/21/cf1f0f10ec7be98056bf126d5185ba57.html
A Brief History of CNNs in Image Segmentation: From R-CNN to Mask R-CNN
Here is a list of papers covered in this post ;)
Model | Goal | Resources |
R-CNN | Object recognition | [paper][code] |
Fast R-CNN | Object recognition | [paper][code] |
Faster R-CNN | Object recognition | [paper][code] |
Mask R-CNN | Image segmentation | [paper][code] |